excalidraw-diagram-generator

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete scripts, examples, and a clear stepwise workflow, but it is verbose and repetitive, and references three template files that do not exist in the bundle.

Suggestions

Remove the duplicated request/"Recommended Workflow" header and consolidate the repeated Python-script benefits into one list to tighten the body's token budget.

Add the missing templates/flowchart-template.json, templates/relationship-template.json, and templates/mindmap-template.json, or drop them from the References section, so all referenced paths resolve.

Move the large Icon Libraries section into a separate reference file (e.g. references/icon-libraries.md) and keep SKILL.md as a concise overview that links to it.

Dimension	Reasoning	Score
Conciseness	The ~614-line body is mostly useful but padded with redundancy — the AWS example repeats its request and "Recommended Workflow" header twice, restates script benefits across multiple sections, and over-explains rationale Claude already grasps. Not a wall of fluff, but clearly tightenable.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands such as `python scripts/add-icon-to-diagram.py <diagram-path> <icon-name> <x> <y> [--label "Text"]` and `add-arrow.py`, plus concrete JSON structure, coordinate gaps (200-300px), hex colors, and fontFamily: 5, matching the top anchor.	3 / 3
Workflow Clarity	A clearly sequenced 6-step workflow (understand → choose type → extract → generate JSON → format → save) is paired with an explicit validation checklist; operations are generative and non-destructive so the absence of a heavy validate-retry loop is acceptable.	3 / 3
Progressive Disclosure	Well-signaled one-level references to existing files (references/excalidraw-schema.md, references/element-types.md, scripts) are undercut by broken references to missing templates/flowchart-template.json, relationship-template.json, and mindmap-template.json, and the monolithic inline Icon Libraries section could itself be split out.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it states concrete capabilities, includes natural trigger phrases, explicitly covers both what and when, and is anchored to a distinct Excalidraw output format. It is concise and avoids fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Generate Excalidraw diagrams from natural language descriptions" and "Outputs .excalidraw JSON files that can be opened directly in Excalidraw" — matching the anchor for listing several specific capabilities.	3 / 3
Completeness	Explicitly answers both what (generate diagrams across listed types, output .excalidraw JSON) and when ("Use when asked to..." with concrete triggers), satisfying the top anchor for both components.	3 / 3
Trigger Term Quality	Provides natural phrasings a user would say — "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", "generate an Excalidraw file" — giving good coverage of likely requests.	3 / 3
Distinctiveness Conflict Risk	The Excalidraw format niche and the defining trigger "generate an Excalidraw file" clearly distinguish it, even though generic terms like "create a diagram" have mild overlap risk with general diagramming skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (614 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ZHangZHengEric/Sage
Path: app/skills/excalidraw-diagram-generator/SKILL.md
Commit: ce79d60

Reviewed: about 19 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.